GridseachCV - ValueError: Found input variables with inconsistent numbers of samples: [33 1]

Question

I am trying to use gridsearchCV with on my keras model, but seem to have ran into a error which i am not sure how to interpret.

Traceback (most recent call last):
  File "keras_cnn_phoneme_generator_fit.py", line 229, in <module>
    grid_results=grid.fit(train_input,train_output)
  File "/home/c/.local/lib/python2.7/site-packages/sklearn/model_selection/_search.py", line 940, in fit
    return self._fit(X, y, groups, ParameterGrid(self.param_grid))
  File "/home/c/.local/lib/python2.7/site-packages/sklearn/model_selection/_search.py", line 541, in _fit
    X, y, groups = indexable(X, y, groups)
  File "/home/c/.local/lib/python2.7/site-packages/sklearn/utils/validation.py", line 206, in indexable
    check_consistent_length(*result)
  File "/home/c/.local/lib/python2.7/site-packages/sklearn/utils/validation.py", line 181, in check_consistent_length
    " samples: %r" % [int(l) for l in lengths])
ValueError: Found input variables with inconsistent numbers of samples: [33, 1]

Here is the model and how i apply it.

def model3(kernel_number = 200, kernel_shape = (window_height,3)):
    #stride = 1
    #dim = 40
    #window_height = 8
    #splits = ((40-8)+1)/1 = 33
    #next(test_generator())
    #next(train_generator(batch_size))

    #kernel_number = 200
    list_of_input = [Input(shape = (window_height,total_frames_with_deltas,3)) for i in range(splits)]
    list_of_conv_output = []
    list_of_max_out = []
    for i in range(splits):
        if splits == 1:
            list_of_conv_output.append(Conv2D(filters = kernel_number , kernel_size = kernel_shape, activation = 'relu')(list_of_input[i]))
            list_of_max_out.append((MaxPooling2D(pool_size=((1,11)))(list_of_conv_output[i])))
        else:
            list_of_conv_output.append(Conv2D(filters = 200 , kernel_size = (window_height,3) , activation = 'relu')(list_of_input[i]))
            list_of_max_out.append((MaxPooling2D(pool_size=((1,11)))(list_of_conv_output[i])))

    merge = keras.layers.concatenate(list_of_max_out)
    print merge.shape
    reshape = Reshape((total_frames/total_frames,-1))(merge)

    dense1 = Dense(units = 1000, activation = 'relu',    name = "dense_1")(reshape)
    dense2 = Dense(units = 1000, activation = 'relu',    name = "dense_2")(dense1)
    dense3 = Dense(units = 145 , activation = 'softmax', name = "dense_3")(dense2)


    model = Model(inputs = list_of_input , outputs = dense3)
    model.compile(loss="categorical_crossentropy", optimizer="SGD" , metrics = [metrics.categorical_accuracy])

    reduce_lr=ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=3, verbose=1, mode='auto', epsilon=0.001, cooldown=0)
    stop  = EarlyStopping(monitor='val_loss', min_delta=0, patience=5, verbose=1, mode='auto')
    log=csv_logger = CSVLogger('/home/c/kaldi-trunk/dnn/training_'+str(total_frames)+"_"+str(dim)+"_"+str(window_height)+"_"+str(batch_size)+".csv")
    checkpoint = ModelCheckpoint(filepath="/media/c/E2302E68302E443F/Timit-dataset/timit/fbank/nn/"+str(total_frames)+"_"+str(dim)+"_"+str(window_height)+"_"+str(batch_size)+".hdf5",save_best_only=True)

    if len(sys.argv) == 7:
        model.load_weigts(weights)

    print model.summary()

    #raw_input("okay?")
    #hist_current = model.fit_generator(train_generator(batch_size),
    #                    steps_per_epoch=10,
    #                    epochs = 100000,
    #                    verbose = 1,
    #                    validation_data = test_generator(),
    #                    validation_steps=1,
    #                    pickle_safe = True,
    #                    workers = 4,
    #                    callbacks = [log,checkpoint])
    return model


#model3()

model = KerasClassifier(build_fn=model3,epochs = 10,batch_size = 1,verbose=1)
kernel_number = [10,50,100,150,200,250]
kernel_shape = [(window_height,3),(window_height,5),(window_height,8)]
param_grid = dict(kernel_number = kernel_number , kernel_shape=kernel_shape)
grid = GridSearchCV(estimator=model, param_grid=param_grid)
train_input,train_output = next(train_generator(1))
grid_results=grid.fit(train_input,train_output)

print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
    print("%f (%f) with: %r" % (mean, stdev, param))

The model has multiple inputs, 33 in total.These inputs are given by a data_generator, which spits out a list of length 33 with numpy.arrays if shape (batch_size, 1 , 40,8,3). Could the problem be that it not able to handle list? or why am i getting this error?

for batch_size = 100

print len(train_input)
print train_input[0].shape
print train_output.shape

33
(100, 8, 45, 3)
(100, 1, 145)

Answer 1

The documentation states:

You can use Sequential Keras models (single-input only) as part of your Scikit-Learn workflow via the wrappers found at keras.wrappers.scikit_learn.py.

So, it is not possible.

I guess a different solution has to be found.